Reinforcement learning · MLD-1011
REINFORCE
A Monte Carlo policy-gradient estimator using sampled returns to weight log-probability gradients.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Optimize a stochastic policy from complete returns.
Original caveat
Baseline subtraction can reduce variance without changing the ideal expected gradient.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: RL · DL · SLM · LLM.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- OpenAI Spinning Up: reinforcement learning ↗ · Consulted
- TRL documentation ↗ · Consulted
- Original reference URL ↗